Fix typos.
This commit is contained in:
parent
610cebd2f1
commit
2219704aaa
14
README.md
14
README.md
@ -164,9 +164,9 @@ model.fit(images, captions, batch_size=16, nb_epoch=100)
|
|||||||
```
|
```
|
||||||
|
|
||||||
In the examples folder, you will find example models for real datasets:
|
In the examples folder, you will find example models for real datasets:
|
||||||
- CIFAR10 small images classification: convnet with realtime data augmentation
|
- CIFAR10 small images classification: Convnet with realtime data augmentation
|
||||||
- IMDB movie reviews: sentiment classification
|
- IMDB movie review sentiment classification: LSTM over sequences of words
|
||||||
- Reuters newswires: topic classification
|
- Reuters newswires topic classification: Multilayer Perceptron
|
||||||
|
|
||||||
## Warning
|
## Warning
|
||||||
|
|
||||||
@ -175,17 +175,17 @@ This is a 0.0.1 alpha release. Feature scope is limited, and wild bugs may appea
|
|||||||
## Current capabilities
|
## Current capabilities
|
||||||
|
|
||||||
- model architectures:
|
- model architectures:
|
||||||
sequential (pipeline of layers)
|
- Sequential (pipeline of layers)
|
||||||
|
|
||||||
- layers:
|
- layers:
|
||||||
- layers.core:
|
- layers.core:
|
||||||
- Dense
|
- Dense
|
||||||
- Dropout
|
- Dropout
|
||||||
- Activation
|
- Activation
|
||||||
|
- Embedding
|
||||||
- Reshape
|
- Reshape
|
||||||
- Flatten
|
- Flatten
|
||||||
- Embedding
|
- RepeatVector
|
||||||
- Repeat
|
|
||||||
- layers.convolutional:
|
- layers.convolutional:
|
||||||
- Convolution2D
|
- Convolution2D
|
||||||
- MaxPooling2D
|
- MaxPooling2D
|
||||||
@ -259,7 +259,7 @@ sudo python setup.py install
|
|||||||
|
|
||||||
## Why this name, Keras?
|
## Why this name, Keras?
|
||||||
|
|
||||||
Keras (κέρας) means _horn_ in Greek. It is a reference to a literary image from ancient Greek and Latin literature, first found in the _Odyssee_, where dream spirits (_Oneiroi_, singular _Oneiros_) are divided between those who deceive men with false visions, who arrive to Earth through a gate of ivory, and those who announce a future that will come to pass, who arrive through a gate of horn. It's a play on the words κέρας (horn) / κραίνω (fulfill), and ἐλέφας (ivory) / ἐλεφαίρομαι (deceive).
|
Keras (κέρας) means _horn_ in Greek. It is a reference to a literary image from ancient Greek and Latin literature, first found in the _Odyssey_, where dream spirits (_Oneiroi_, singular _Oneiros_) are divided between those who deceive men with false visions, who arrive to Earth through a gate of ivory, and those who announce a future that will come to pass, who arrive through a gate of horn. It's a play on the words κέρας (horn) / κραίνω (fulfill), and ἐλέφας (ivory) / ἐλεφαίρομαι (deceive).
|
||||||
|
|
||||||
Keras was developed as part of the research effort of project ONEIROS (Open-ended Neuro-Electronic Intelligent Robot Operating System).
|
Keras was developed as part of the research effort of project ONEIROS (Open-ended Neuro-Electronic Intelligent Robot Operating System).
|
||||||
|
|
||||||
|
@ -116,7 +116,7 @@ class RepeatVector(Layer):
|
|||||||
|
|
||||||
class Dense(Layer):
|
class Dense(Layer):
|
||||||
'''
|
'''
|
||||||
Just your regular fully connecter NN layer.
|
Just your regular fully connected NN layer.
|
||||||
'''
|
'''
|
||||||
def __init__(self, input_dim, output_dim, init='uniform', activation='linear', weights=None):
|
def __init__(self, input_dim, output_dim, init='uniform', activation='linear', weights=None):
|
||||||
self.init = initializations.get(init)
|
self.init = initializations.get(init)
|
||||||
@ -141,7 +141,7 @@ class Dense(Layer):
|
|||||||
|
|
||||||
class Embedding(Layer):
|
class Embedding(Layer):
|
||||||
'''
|
'''
|
||||||
Turns a list of integers into a dense vector of fixed size.
|
Turn a list of integers >=0 into a dense vector of fixed size.
|
||||||
eg. [4, 50, 123, 26] -> [0.25, 0.1]
|
eg. [4, 50, 123, 26] -> [0.25, 0.1]
|
||||||
|
|
||||||
@input_dim: size of vocabulary (highest input integer + 1)
|
@input_dim: size of vocabulary (highest input integer + 1)
|
||||||
|
Loading…
Reference in New Issue
Block a user